Blog
For shorter decision guides, use Fast Answers. The archive below is for the long-form articles.
All articles
-
AI Agents
Harness Engineering for AI Agents: Designing Control Loops
How the control code around an AI agent authorizes tools, preserves progress, verifies completion, and earns each added component through ablation.
-
Model Engineering · AI Infrastructure
Model Quantization Guide: Foundations to Production Serving
A practical guide to choosing LLM and diffusion-model quantization paths by bottleneck, hardware, runtime kernel, calibration data, and deploy checks.
-
AI Agents
AI Agent Memory: Schema-Guided State and Provenance
Why production AI agents need schema-guided memory with temporal validity, provenance, and structured conflict handling instead of raw text vector recall.
-
AI Agents
AI Agent Evaluation in Production: Traces to Test Suites
How to evaluate production AI agents by turning traces into versioned regression datasets, trajectory metrics, calibrated judges, and CI gates.
-
AI Agents
Long-Running AI Agent Runtime: Sessions and Checkpoints
How to run long-running AI agents in production with sessions, harnesses, sandboxes, checkpoints, traces, and deployment patterns that recover cleanly.
-
Retrieval and Language Systems
RAG Evaluation Metrics: Retrieval, Reranking, Generation
RAG evaluation metrics for parsing, retrieval, reranking, generation, citations, and production telemetry, with code and failure modes.
-
AI Agents
AI Agent Security: Permissions, Sandboxes, and MCP Threats
Why LLM guardrails are not enough for AI agent security, and where permissions, sandboxes, HITL, MCP scoping, and policy checks fit.
-
Retrieval and Language Systems
NER Guide 2026: GLiNER, spaCy, Transformers, and LLMs
NER in 2026 means choosing between GLiNER, spaCy, Transformers, and LLM extraction for latency, accuracy, and schema control.
-
AI Agents
AI Agent Tool Use: MCP, CLI, Skills, and Code Execution
Compare JSON tool calling, MCP, Skills, CLI, and code execution for AI agents, with ACI design rules and the production trade-offs that matter.
-
Model Engineering · AI Infrastructure
LLM Engineering Guide: 45 Concepts for Production Systems
A practitioner's reference to 45 LLM engineering concepts for production systems, spanning inference, training, architecture, deployment, and operations.
-
Retrieval and Language Systems
OCR in 2026: Classical Pipelines, VLMs, and Document AI
OCR in 2026 means choosing between classical pipelines and VLMs for text, layout, tables, and document extraction.
-
AI Infrastructure
Data Processing Engines: Polars, DataFusion, Ray, and Spark
Benchmarks comparing Polars, DataFusion, Daft, Ray Data, Pandas, and Spark on tabular and multimodal workloads, with code and decision rules.
-
AI Agents
AI Agent Memory Architecture: Checkpoints and Vector Stores
How to design AI agent memory with checkpoints, PostgreSQL or Redis, vector stores such as Qdrant, and file-based memory for long-running systems.
-
Retrieval and Language Systems
Search Ranking Stack: BM25, Embeddings, and Reranking
How to build a search ranking stack with BM25, dense embeddings, hybrid RRF, cross-encoder reranking, and LLM listwise reranking on Amazon ESCI.
-
AI Agents
AI Agent Reasoning Loops: ReAct, ReWOO, Plan-and-Execute
Compare ReAct, ReWOO, and Plan-and-Execute for AI agents. LangGraph examples show how each loop trades adaptability for cost, latency, and planning structure.
-
Model Engineering
DeepSeek mHC: Manifold-Constrained Hyper-Connections
A technical walkthrough of DeepSeek's Manifold-Constrained Hyper-Connections (mHC), residual stream width scaling, Sinkhorn routing, and training stability.
-
AI Agents
Enterprise RAG Challenge 3: Lessons from Public Entries
What public Enterprise RAG Challenge 3 submissions reveal about prompt iteration, validation, context strategy, tool wrappers, and agent architecture.
-
Model Engineering
LLM Fine-Tuning Guide: LoRA, QLoRA, Unsloth, Axolotl
When to fine-tune LLMs, when to use RAG or prompting, and how LoRA, QLoRA, DoRA, Unsloth, Axolotl, datasets, evals, and deployment fit.
-
AI Agents · Model Engineering
Schema-Guided Reasoning: vLLM, xgrammar, and Pydantic
How Schema-Guided Reasoning uses vLLM, xgrammar, Pydantic schemas, and constrained decoding to enforce structurally valid LLM outputs.
-
Model Engineering · AI Infrastructure
LoRAX Serving Guide: LoRA Adapters on Kubernetes at Scale
Evaluate and deploy LoRAX for long-tail LoRA serving, with current APIs, Kubernetes chart hardening, adapter security, cache-aware routing, and vLLM trade-offs.
-
AI Agents
Domain-Driven Design for AI Agents: Contexts and Rules
How domain-driven design helps AI agents use shared language, bounded contexts, services, repositories, and deterministic business rules.
-
AI Agents
Context Engineering for AI Agents: Memory and Tools
How to design context engineering for AI agents: context windows, instruction hierarchy, retrieval, memory, tools, guardrails, provenance, and compression.
-
AI Agents · Developer Tooling
MCP Server Tutorial: Build with Python, uv, and FastMCP
Build a custom MCP server with uv and FastMCP, expose ML feature-store tools, test them locally, and connect the server to Claude Desktop.
-
Model Engineering
Open-Weight LLM Variants, Formats, and Quantization
How to read open-weight model names by separating training role, architecture, quantization method, storage format, runtime, and hardware fit.
-
Developer Tooling
Stable Diffusion on macOS: Local Image Tools Compared
Compare local image-generation tools on macOS by setup, model support, workflow control, reproducibility, extensions, and maintenance status.
-
Model Engineering · Developer Tooling
Local LLMs on macOS: Ollama, LM Studio, MLX, llama.cpp
Compare local LLM tools on macOS by interface, model format, memory headroom, API exposure, and Apple Silicon development workflow.
-
Developer Tooling
pyproject.toml Guide: Packaging, Dependencies, and Tools
How pyproject.toml works for build systems, project metadata, runtime dependencies, development groups, CLI entry points, and tool configuration.
-
Developer Tooling
Zsh Startup Files: .zprofile vs .zshrc on macOS and Linux
Zsh startup files explained: when ~/.zprofile and ~/.zshrc load on macOS and Linux, what belongs in each file, and how to diagnose the running shell mode.
-
AI Infrastructure
MLOps vs LLMOps: Infrastructure for Foundation Models
What foundation models changed in MLOps: release units, retrieval, tools, evaluation, tracing, serving, and operational risk.
-
Model Engineering · AI Infrastructure
Scaling LLMs with Multi-GPU and Multi-Node Parallelism
How to scale large language models across GPUs and nodes with data, fully sharded, tensor, pipeline, context, and expert parallelism.
-
Developer Tooling
MacBook Setup for AI Engineering: macOS Tools and Workflow
A MacBook setup checklist for AI engineering: Xcode tools, Homebrew, Python with uv, Docker, terminal setup, and VS Code.
-
Developer Tooling
uv on macOS: Managing Python Versions, Projects, and Tools
How I use uv on macOS for Python installs, project dependencies, lock files, inline scripts, and one-off CLI tools.